Introduction

The API reference describes the RESTful APIs you can use to interact with the Z.AI platform.

Z.AI provides standard HTTP API interfaces that support multiple programming languages and development environments, with SDKs also available.

API Endpoint

Z.ai Platform’s general API endpoint is as follows:

https://api.z.ai/api/paas/v4

When using GLM Coding Plan, please follow the tutorial to configure your dedicated endpoint.

Authentication

The Z.AI API uses the standard HTTP Bearer for authentication. An API key is required, which you can create or manage on the API Keys Page. API keys should be provided via HTTP Bearer Authentication in HTTP Request Headers.

Authorization: Bearer ZAI_API_KEY

Playground

The API Playground allows developers to quickly try out API calls. Simply click Try it on the API details page to get started.

On the API details page, there are many interactive options, such as switching input types, switching tabs, and adding new content.
You can click Add an item or Add new property to add more properties the API need.
Note that when switching the tabs, the previous properties value you need re-input or re-switch.

API Usage Bundle Billing Rules

If you purchase an API usage bundle for a model, we will prioritize consuming the included usage quota from that bundle. Once the bundle is exhausted, your API access remains fully unaffected — you can continue making calls as usual with no service interruption whatsoever. The only change is that, going forward, each API call will be billed at the standard pay-as-you-go rate, with the corresponding charges deducted directly from your account.

Call Examples

curl -X POST "https://api.z.ai/api/paas/v4/chat/completions" \
-H "Content-Type: application/json" \
-H "Accept-Language: en-US,en" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
    "model": "glm-5.3",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful AI assistant."
        },
        {
            "role": "user",
            "content": "Hello, please introduce yourself."
        }
    ],
    "temperature": 1.0,
    "stream": true
}'

Install SDK

# Install latest version
pip install zai-sdk

# Or specify version
pip install zai-sdk==0.2.3

Verify Installation

import zai
print(zai.__version__)

Usage Example

from zai import ZaiClient

# Initialize client
client = ZaiClient(api_key="YOUR_API_KEY")

# Create chat completion request
response = client.chat.completions.create(
    model="glm-5.3",
    messages=[
        {
            "role": "system",
            "content": "You are a helpful AI assistant."
        },
        {
            "role": "user",
            "content": "Hello, please introduce yourself."
        }
    ]
)

# Get response
print(response.choices[0].message.content)

Install SDKMaven

<dependency>
    <groupId>ai.z.openapi</groupId>
    <artifactId>zai-sdk</artifactId>
    <version>0.3.5</version>
</dependency>

Gradle (Groovy)

implementation 'ai.z.openapi:zai-sdk:0.3.5'

Usage Example

import ai.z.openapi.ZaiClient;
import ai.z.openapi.service.model.*;
import java.util.Arrays;

public class QuickStart {
    public static void main(String[] args) {
        // Initialize client
        ZaiClient client = ZaiClient.builder().ofZAI()
            .apiKey("YOUR_API_KEY")
            .build();

        // Create chat completion request
        ChatCompletionCreateParams request = ChatCompletionCreateParams.builder()
            .model("glm-5.3")
            .messages(Arrays.asList(
                ChatMessage.builder()
                    .role(ChatMessageRole.USER.value())
                    .content("Hello, who are you?")
                    .build()
            ))
            .stream(false)
            .build();

        // Send request
        ChatCompletionResponse response = client.chat().createChatCompletion(request);

        // Get response
        System.out.println(response.getData().getChoices().get(0).getMessage().getContent());
    }
}

Install SDK

# Install or upgrade to latest version
pip install --upgrade 'openai>=1.0'

Verify Installation

python -c "import openai; print(openai.__version__)"

Usage Example

from openai import OpenAI

client = OpenAI(
    api_key="your-Z.AI-api-key",
    base_url="https://api.z.ai/api/paas/v4/"
)

completion = client.chat.completions.create(
    model="glm-5.3",
    messages=[
        {"role": "system", "content": "You are a smart and creative novelist"},
        {"role": "user", "content": "Please write a short fairy tale story as a fairy tale master"}
    ]
)

print(completion.choices[0].message.content)

Install SDK

# Install or upgrade to latest version
npm install openai

# Or using yarn
yarn add openai

Usage Example

import OpenAI from "openai";

const client = new OpenAI({
    apiKey: "your-Z.AI-api-key",
    baseURL: "https://api.z.ai/api/paas/v4/"
});

async function main() {
    const completion = await client.chat.completions.create({
        model: "glm-5.3",
        messages: [
            { role: "system", content: "You are a helpful AI assistant." },
            { role: "user", content: "Hello, please introduce yourself." }
        ]
    });

    console.log(completion.choices[0].message.content);
}

main();

Install SDKMaven

<dependency>
    <groupId>com.openai</groupId>
    <artifactId>openai-java</artifactId>
    <version>2.20.1</version>
</dependency>

Gradle (Groovy)

implementation 'com.openai:openai-java:2.20.1'

Usage Example

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

public class QuickStart {
    public static void main(String[] args) {
        // Initialize client
        OpenAIClient client = OpenAIOkHttpClient.builder()
            .apiKey("your-Z.AI-api-key")
            .baseUrl("https://api.z.ai/api/paas/v4/")
            .build();

        // Create chat completion request
        ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
            .addSystemMessage("You are a helpful AI assistant.")
            .addUserMessage("Hello, please introduce yourself.")
            .model("glm-5.3")
            .build();

        // Send request and get response
        ChatCompletion chatCompletion = client.chat().completions().create(params);
        Object response = chatCompletion.choices().get(0).message().content();

        System.out.println(response);
    }
}

Using the APIs

Model API

Image API

Video API

Audio API

Tool API

Agent API

API Endpoint

Authentication

Playground

API Usage Bundle Billing Rules

Call Examples

​API Endpoint

​Authentication

​Playground

​API Usage Bundle Billing Rules

​Call Examples

API Endpoint

Authentication

Playground

API Usage Bundle Billing Rules

Call Examples